Using GridWay ¶

Documentation ¶

The following guide is available: User's Guide 5.8

Login with proxy certificate ¶

grid-proxy-init

Your identity: /C=DE/O=GermanGrid/OU=ZAH/CN=Klaus Rieger
Enter GRID pass phrase for this identity:
Creating proxy .................................................... Done
Your proxy is valid until: Sat Jan 21 03:42:00 2012

gsissh dgsi.zah.uni-heidelberg.de

Last login: Fri Jan 20 10:07:08 2012 from asterope.ari.uni-heidelberg.de

Simple Test ¶

Write Job Template ¶

vi gridway.jt

Edit (i)

EXECUTABLE="/bin/echo"
ARGUMENTS="dgsi.zah.uni-heidelberg.de"

Save (ESC :wq)

Run Job ¶

gwsubmit -t gridway.jt

gwps

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   pend ---- 17:27:11 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

gwps (after some seconds)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   prol ---- 17:27:11 --:--:-- 0:00:00 0:00:00 --   gridway.jt      astar.aip.de/Fork

gwps (after some seconds)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   wrap ---- 17:27:11 --:--:-- 0:00:00 0:00:03 --   gridway.jt      astar.aip.de/Fork

gwps (after some seconds)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   wrap pend 17:27:11 --:--:-- 0:00:04 0:00:03 --   gridway.jt      astar.aip.de/Fork

gwps (after some seconds)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   epil ---- 17:27:11 --:--:-- 0:00:06 0:00:04 --   gridway.jt      astar.aip.de/Fork

gwps (after some seconds)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork

Hint: Works on dgsi.zah.uni-heidelberg.de, only, because gwsubmit not available on most other hosts!

Watch Log Files ¶

cd $GW_LOCATION/var/

ls

0  globus-gw.log  gwd.log  gwd.port  sched.log

cd 0/

ls

job.conf  job.contact  job.env  job.history  job.log  job.rsl.0  job.state  job.template  stderr.wrapper.0  stdout.wrapper.0

more job.log (or any other file in this folder)

Sat Jan 28 17:27:11 2012 [DM][I]: ----------- Job configuration file (gridway.jt) values -----------
Sat Jan 28 17:27:11 2012 [DM][I]:       EXECUTABLE             : /bin/echo
Sat Jan 28 17:27:11 2012 [DM][I]:       ARGUMENTS              : dgsi.zah.uni-heidelberg.de
Sat Jan 28 17:27:11 2012 [DM][I]:       INPUT_FILES   (Total 0):
Sat Jan 28 17:27:11 2012 [DM][I]:       OUTPUT_FILES  (Total 0):
Sat Jan 28 17:27:11 2012 [DM][I]:       RESTART_FILES (Total 0):
Sat Jan 28 17:27:11 2012 [DM][I]:       STDIN_FILE             : /dev/null
Sat Jan 28 17:27:11 2012 [DM][I]:       STDOUT_FILE            : stdout.${JOB_ID}
Sat Jan 28 17:27:11 2012 [DM][I]:       STDERR_FILE            : stderr.${JOB_ID}
Sat Jan 28 17:27:11 2012 [DM][I]:       REQUIREMENTS           :
Sat Jan 28 17:27:11 2012 [DM][I]:       RANK                   :
Sat Jan 28 17:27:11 2012 [DM][I]:       RESCHEDULING_INTERVAL  : 0
Sat Jan 28 17:27:11 2012 [DM][I]:       RESCHEDULING_THRESHOLD : 300
Sat Jan 28 17:27:11 2012 [DM][I]:       SUSPENSION_TIMEOUT     : 600
Sat Jan 28 17:27:11 2012 [DM][I]:       CPULOAD_THRESHOLD      : 50
Sat Jan 28 17:27:11 2012 [DM][I]:       RESCHEDULE_ON_FAILURE  : yes
Sat Jan 28 17:27:11 2012 [DM][I]:       NUMBER_OF_RETRIES      : 1
Sat Jan 28 17:27:11 2012 [DM][I]:       CHECKPOINT_INTERVAL    : 0
Sat Jan 28 17:27:11 2012 [DM][I]:       CHECKPOINT_URL         :
Sat Jan 28 17:27:11 2012 [DM][I]:       WRAPPER                : /usr/local/gridway-5.8/libexec/gw_wrapper.sh
Sat Jan 28 17:27:11 2012 [DM][I]:       MONITOR                :
Sat Jan 28 17:27:11 2012 [DM][I]:       PRE_WRAPPER            :
Sat Jan 28 17:27:11 2012 [DM][I]:       PRE_WRAPPER_ARGUMENTS  :
Sat Jan 28 17:27:11 2012 [DM][I]:       TYPE                   : single
Sat Jan 28 17:27:11 2012 [DM][I]:       NP                     : 1
Sat Jan 28 17:27:11 2012 [DM][I]:       DEADLINE               : 0:00:00 0
Sat Jan 28 17:27:11 2012 [DM][I]: ----------------------------------------------------------
Sat Jan 28 17:27:11 2012 [DM][I]: New state is PENDING.
Sat Jan 28 17:27:19 2012 [DM][I]: New state is PROLOG.
...
Sat Jan 28 17:27:22 2012 [DM][I]: New state is WRAPPER.
...
Sat Jan 28 17:27:26 2012 [EM][I]: New execution state is PENDING.
Sat Jan 28 17:27:28 2012 [EM][I]: New execution state is DONE.
...
Sat Jan 28 17:27:28 2012 [DM][I]: New state is EPILOG_STD.
...
Sat Jan 28 17:27:30 2012 [DM][I]: New state is EPILOG.
...
Sat Jan 28 17:27:33 2012 [DM][I]: New state is DONE.
Sat Jan 28 17:27:33 2012 [DM][I]: Job done, history:
Sat Jan 28 17:27:33 2012 [DM][I]: ----------- Job history record -----------
Sat Jan 28 17:27:33 2012 [IM][I]:       -------------- Host info.  --------------
Sat Jan 28 17:27:33 2012 [IM][I]:       Name = astar.aip.de
Sat Jan 28 17:27:33 2012 [IM][I]:       OS   = Linux 2.6.32-rc5_AIP
Sat Jan 28 17:27:33 2012 [IM][I]:       CPU  = x86_64 (x86_64) at 3010 MHz
Sat Jan 28 17:27:33 2012 [IM][I]:       Mem  = 87 of 3145 MB
Sat Jan 28 17:27:33 2012 [IM][I]:       Disk = 158610 of 499862 MB
Sat Jan 28 17:27:33 2012 [IM][I]:       LRMS = fork (Fork) with 2 nodes
Sat Jan 28 17:27:33 2012 [IM][I]:                         NC FNC    MT   MCT  MC MRJ MJQ
Sat Jan 28 17:27:33 2012 [IM][I]:       QUEUE= default  (  2   1     0    -1   0  -1   0), enabled status, NULL type, 0 priority
Sat Jan 28 17:27:33 2012 [IM][I]:       -----------------------------------------
Sat Jan 28 17:27:33 2012 [DM][I]:       Host GRAM contact = astar.aip.de/Fork
Sat Jan 28 17:27:33 2012 [DM][I]:       Remote job dir    = gsiftp://astar.aip.de/~/.gw_agrid107_0/
Sat Jan 28 17:27:33 2012 [DM][I]:       Host Rank         = 0
Sat Jan 28 17:27:33 2012 [DM][I]:       Submission tries  = 1
Sat Jan 28 17:27:33 2012 [DM][I]:       Start time        = 1327768039
Sat Jan 28 17:27:33 2012 [DM][I]:       Exit Time         = 1327768053
Sat Jan 28 17:27:33 2012 [DM][I]:       Prolog Time       = 3
Sat Jan 28 17:27:33 2012 [DM][I]:       Wrapper Time      = 6
Sat Jan 28 17:27:33 2012 [DM][I]:       Epilog Time       = 5
Sat Jan 28 17:27:33 2012 [DM][I]:       Migration Time    = 0
Sat Jan 28 17:27:33 2012 [DM][I]: ------------------------------------------

cd ~

gwhistory 0 (or any other existing Job Identifier)

HID START    END      PROLOG  WRAPPER EPILOG  MIGR    REASON QUEUE    HOST
2   17:27:19 17:27:33 0:00:03 0:00:06 0:00:05 0:00:00 ----   default  astar.aip.de/Fork

Multiple Job Test ¶

Write Job Template ¶

vi ten_gridway.sh

Edit (i)

gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt
gwsubmit -t gridway.jt

Save (ESC :wq)

chmod +x ten_gridway.sh

Run Jobs ¶

./ten_gridway.sh

gwps -c 1 (refresh job information every second)

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   2   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   3   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   4   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astar.aip.de/Fork
agrid107:0   2   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   wrap ---- 17:41:26 --:--:-- 0:00:00 0:00:04 --   gridway.jt      astar.aip.de/Fork
agrid107:0   2   wrap pend 17:41:26 --:--:-- 0:00:02 0:00:02 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   wrap pend 17:41:26 --:--:-- 0:00:01 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   wrap pend 17:41:26 --:--:-- 0:00:01 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   wrap pend 17:41:26 --:--:-- 0:00:01 0:00:04 --   gridway.jt      astar.aip.de/Fork
agrid107:0   2   epil ---- 17:41:26 --:--:-- 0:00:03 0:00:02 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   wrap actv 17:41:26 --:--:-- 0:00:02 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:04 --   gridway.jt      astar.aip.de/Fork
agrid107:0   2   epil ---- 17:41:26 --:--:-- 0:00:03 0:00:03 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:04 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:04 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   6   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   7   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   8   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:01 --   gridway.jt      astar.aip.de/Fork
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   wrap pend 17:41:26 --:--:-- 0:00:02 0:00:01 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   wrap pend 17:41:26 --:--:-- 0:00:01 0:00:02 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   wrap ---- 17:41:26 --:--:-- 0:00:00 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   wrap ---- 17:41:26 --:--:-- 0:00:00 0:00:03 --   gridway.jt      astar.aip.de/Fork
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   epil ---- 17:41:26 --:--:-- 0:00:03 0:00:03 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   epil ---- 17:41:26 --:--:-- 0:00:04 0:00:02 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   epil ---- 17:41:26 --:--:-- 0:00:03 0:00:03 --   gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:04 --   gridway.jt      astar.aip.de/Fork
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   done ---- 17:41:26 17:41:56 0:00:03 0:00:04 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   done ---- 17:41:26 17:42:00 0:00:04 0:00:07 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   done ---- 17:41:26 17:42:00 0:00:03 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   done ---- 17:41:26 17:42:00 0:00:02 0:00:09 0    gridway.jt      astar.aip.de/Fork
agrid107:0   9   pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --
agrid107:0   10  pend ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      --

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   done ---- 17:41:26 17:41:56 0:00:03 0:00:04 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   done ---- 17:41:26 17:42:00 0:00:04 0:00:07 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   done ---- 17:41:26 17:42:00 0:00:03 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   done ---- 17:41:26 17:42:00 0:00:02 0:00:09 0    gridway.jt      astar.aip.de/Fork
agrid107:0   9   prol ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   10  prol ---- 17:41:26 --:--:-- 0:00:00 0:00:00 --   gridway.jt      astar.aip.de/Fork

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   done ---- 17:41:26 17:41:56 0:00:03 0:00:04 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   done ---- 17:41:26 17:42:00 0:00:04 0:00:07 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   done ---- 17:41:26 17:42:00 0:00:03 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   done ---- 17:41:26 17:42:00 0:00:02 0:00:09 0    gridway.jt      astar.aip.de/Fork
agrid107:0   9   wrap pend 17:41:26 --:--:-- 0:00:01 0:00:01 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   10  prol ---- 17:41:26 --:--:-- 0:00:00 0:00:02 --   gridway.jt      astar.aip.de/Fork

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   done ---- 17:41:26 17:41:56 0:00:03 0:00:04 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   done ---- 17:41:26 17:42:00 0:00:04 0:00:07 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   done ---- 17:41:26 17:42:00 0:00:03 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   done ---- 17:41:26 17:42:00 0:00:02 0:00:09 0    gridway.jt      astar.aip.de/Fork
agrid107:0   9   epil ---- 17:41:26 --:--:-- 0:00:02 0:00:03 --   gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   10  wrap pend 17:41:26 --:--:-- 0:00:02 0:00:03 --   gridway.jt      astar.aip.de/Fork

USER         JID DM   EM   START    END      EXEC    XFER    EXIT NAME            HOST
agrid107:0   0   done ---- 17:27:11 17:27:33 0:00:06 0:00:08 0    gridway.jt      astar.aip.de/Fork
agrid107:0   1   done ---- 17:41:26 17:41:46 0:00:02 0:00:10 0    gridway.jt      astar.aip.de/Fork
agrid107:0   2   done ---- 17:41:26 17:41:42 0:00:03 0:00:05 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   3   done ---- 17:41:26 17:41:45 0:00:02 0:00:09 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   4   done ---- 17:41:26 17:41:44 0:00:02 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   5   done ---- 17:41:26 17:41:56 0:00:03 0:00:04 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   6   done ---- 17:41:26 17:42:00 0:00:04 0:00:07 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   7   done ---- 17:41:26 17:42:00 0:00:03 0:00:08 0    gridway.jt      astrodata.astrogrid-d.org/Fork
agrid107:0   8   done ---- 17:41:26 17:42:00 0:00:02 0:00:09 0    gridway.jt      astar.aip.de/Fork
agrid107:0   9   done ---- 17:41:26 17:42:09 0:00:02 0:00:03 0    gridway.jt      titan.ari.uni-heidelberg.de/Fork
agrid107:0   10  done ---- 17:41:26 17:42:16 0:00:03 0:00:09 0    gridway.jt      astar.aip.de/Fork

* Exit (Ctrl-Z)

[1]+  Stopped                 gwps -c 1

Hint: Works on dgsi.zah.uni-heidelberg.de, only, because gwsubmit not available on most other hosts!

Watch Log Files ¶

cd $GW_LOCATION/var/

ls

0  1  10  2  3  4  5  6  7  8  9  globus-gw.log  gwd.log  gwd.port  sched.log

cd 1/ (or any other existing Job Identifier)

ls

job.conf  job.contact  job.env  job.history  job.log  job.rsl.0  job.state  job.template  stderr.wrapper.0  stdout.wrapper.0

more job.log (or any other file in this folder)

Sat Jan 28 17:41:26 2012 [DM][I]: ----------- Job configuration file (gridway.jt) values -----------
Sat Jan 28 17:41:26 2012 [DM][I]:       EXECUTABLE             : /bin/echo
Sat Jan 28 17:41:26 2012 [DM][I]:       ARGUMENTS              : dgsi.zah.uni-heidelberg.de
Sat Jan 28 17:41:26 2012 [DM][I]:       INPUT_FILES   (Total 0):
Sat Jan 28 17:41:26 2012 [DM][I]:       OUTPUT_FILES  (Total 0):
Sat Jan 28 17:41:26 2012 [DM][I]:       RESTART_FILES (Total 0):
Sat Jan 28 17:41:26 2012 [DM][I]:       STDIN_FILE             : /dev/null
Sat Jan 28 17:41:26 2012 [DM][I]:       STDOUT_FILE            : stdout.${JOB_ID}
Sat Jan 28 17:41:26 2012 [DM][I]:       STDERR_FILE            : stderr.${JOB_ID}
Sat Jan 28 17:41:26 2012 [DM][I]:       REQUIREMENTS           :
Sat Jan 28 17:41:26 2012 [DM][I]:       RANK                   :
Sat Jan 28 17:41:26 2012 [DM][I]:       RESCHEDULING_INTERVAL  : 0
Sat Jan 28 17:41:26 2012 [DM][I]:       RESCHEDULING_THRESHOLD : 300
Sat Jan 28 17:41:26 2012 [DM][I]:       SUSPENSION_TIMEOUT     : 600
Sat Jan 28 17:41:26 2012 [DM][I]:       CPULOAD_THRESHOLD      : 50
Sat Jan 28 17:41:26 2012 [DM][I]:       RESCHEDULE_ON_FAILURE  : yes
Sat Jan 28 17:41:26 2012 [DM][I]:       NUMBER_OF_RETRIES      : 1
Sat Jan 28 17:41:26 2012 [DM][I]:       CHECKPOINT_INTERVAL    : 0
Sat Jan 28 17:41:26 2012 [DM][I]:       CHECKPOINT_URL         :
Sat Jan 28 17:41:26 2012 [DM][I]:       WRAPPER                : /usr/local/gridway-5.8/libexec/gw_wrapper.sh
Sat Jan 28 17:41:26 2012 [DM][I]:       MONITOR                :
Sat Jan 28 17:41:26 2012 [DM][I]:       PRE_WRAPPER            :
Sat Jan 28 17:41:26 2012 [DM][I]:       PRE_WRAPPER_ARGUMENTS  :
Sat Jan 28 17:41:26 2012 [DM][I]:       TYPE                   : single
Sat Jan 28 17:41:26 2012 [DM][I]:       NP                     : 1
Sat Jan 28 17:41:26 2012 [DM][I]:       DEADLINE               : 0:00:00 0
Sat Jan 28 17:41:26 2012 [DM][I]: ----------------------------------------------------------
Sat Jan 28 17:41:26 2012 [DM][I]: New state is PENDING.
Sat Jan 28 17:41:34 2012 [DM][I]: New state is PROLOG.
...
Sat Jan 28 17:41:38 2012 [DM][I]: New state is WRAPPER.
...
Sat Jan 28 17:41:38 2012 [EM][I]: New execution state is PENDING.
Sat Jan 28 17:41:40 2012 [EM][I]: New execution state is ACTIVE.
Sat Jan 28 17:41:40 2012 [EM][I]: New execution state is DONE.
...
Sat Jan 28 17:41:40 2012 [DM][I]: New state is EPILOG_STD.
...
Sat Jan 28 17:41:43 2012 [DM][I]: New state is EPILOG.
...
Sat Jan 28 17:41:46 2012 [DM][I]: New state is DONE.
Sat Jan 28 17:41:46 2012 [DM][I]: Job done, history:
Sat Jan 28 17:41:46 2012 [DM][I]: ----------- Job history record -----------
Sat Jan 28 17:41:46 2012 [IM][I]:       -------------- Host info.  --------------
Sat Jan 28 17:41:46 2012 [IM][I]:       Name = astar.aip.de
Sat Jan 28 17:41:46 2012 [IM][I]:       OS   = Linux 2.6.32-rc5_AIP
Sat Jan 28 17:41:46 2012 [IM][I]:       CPU  = x86_64 (x86_64) at 3010 MHz
Sat Jan 28 17:41:46 2012 [IM][I]:       Mem  = 87 of 3145 MB
Sat Jan 28 17:41:46 2012 [IM][I]:       Disk = 158609 of 499862 MB
Sat Jan 28 17:41:46 2012 [IM][I]:       LRMS = fork (Fork) with 2 nodes
Sat Jan 28 17:41:46 2012 [IM][I]:                         NC FNC    MT   MCT  MC MRJ MJQ
Sat Jan 28 17:41:46 2012 [IM][I]:       QUEUE= default  (  2   1     0    -1   0  -1   0), enabled status, NULL type, 0 priority
Sat Jan 28 17:41:46 2012 [IM][I]:       -----------------------------------------
Sat Jan 28 17:41:46 2012 [DM][I]:       Host GRAM contact = astar.aip.de/Fork
Sat Jan 28 17:41:46 2012 [DM][I]:       Remote job dir    = gsiftp://astar.aip.de/~/.gw_agrid107_1/
Sat Jan 28 17:41:46 2012 [DM][I]:       Host Rank         = 0
Sat Jan 28 17:41:46 2012 [DM][I]:       Submission tries  = 1
Sat Jan 28 17:41:46 2012 [DM][I]:       Start time        = 1327768894
Sat Jan 28 17:41:46 2012 [DM][I]:       Exit Time         = 1327768906
Sat Jan 28 17:41:46 2012 [DM][I]:       Prolog Time       = 4
Sat Jan 28 17:41:46 2012 [DM][I]:       Wrapper Time      = 2
Sat Jan 28 17:41:46 2012 [DM][I]:       Epilog Time       = 6
Sat Jan 28 17:41:46 2012 [DM][I]:       Migration Time    = 0
Sat Jan 28 17:41:46 2012 [DM][I]: ------------------------------------------

cd ~

gwhistory 1 (or any other existing Job Identifier)

HID START    END      PROLOG  WRAPPER EPILOG  MIGR    REASON QUEUE    HOST
2   17:41:34 17:41:46 0:00:04 0:00:02 0:00:06 0:00:00 ----   default  astar.aip.de/Fork

External Test with Nbody6++ ¶

gsissh mintaka.ari.uni-heidelberg.de

svn co http://svn.ari.uni-heidelberg.de/repos/nbody/deployment/branches/0.2.x nb6deployment

A    nb6deployment/monitor.sh
A    nb6deployment/tmp
A    nb6deployment/kill.sh
A    nb6deployment/scripts
A    nb6deployment/scripts/common.sh
A    nb6deployment/scripts/jobdescription.sh
A    nb6deployment/scripts/stats
A    nb6deployment/scripts/stats/paramread.sh
A    nb6deployment/scripts/stats/stats.sh
A    nb6deployment/CHANGES
A    nb6deployment/var
A    nb6deployment/var/in5000-250
A    nb6deployment/var/plugins
A    nb6deployment/var/plugins/install_plugins.sh
A    nb6deployment/var/plugins/src
A    nb6deployment/var/plugins/src/demo_plugin
A    nb6deployment/var/plugins/src/plugin_template.sh
A    nb6deployment/var/in10k.comment
A    nb6deployment/var/in32k.comment
A    nb6deployment/var/in1000.comment
A    nb6deployment/var/in1000r.comment
A    nb6deployment/var/in5000.ktg.sev
A    nb6deployment/var/in5000.comment
A    nb6deployment/outfiles
A    nb6deployment/libexec
A    nb6deployment/libexec/plugins
A    nb6deployment/libexec/hosts.env
A    nb6deployment/libexec/nb6_wrapper.sh
A    nb6deployment/status.sh
A    nb6deployment/submit.sh
A    nb6deployment/README
Checked out revision 112.

cd nb6deployment/

./submit.sh -h

Submits Nbody6++ jobs to Globus nodes.
Usage: ./submit.sh [options] <parameter-file>

Options:
  -d                  Delegate full credential. [no]
  -g host             Submits the job to <host>. [hydra.ari.uni-heidelberg.de]
  -h                  Print this help.
  -m                  Enable MPI. (Experimental).
  -n                  Disable batch mode.
  -q queue            Use queue <queue>.
  -s                  Enable job statistics (Experimental).
  -t job-manager      Use <job-manager> as Globus Job Manager. [GW]

Stage-in Options:
  -fr file            Stage-in a common-block file for restart.
  -fd file            Stage-in a file for initial data of m,r,v.

Example: ./submit.sh -d var/in1000.comment
          (Option -d must be used to provide a proxy for GridWay.)

Nbody6++ deployment package for AstroGrid-D, v0.2.0-pre ($Revision: 35 $)

./submit.sh -g dgsi.zah.uni-heidelberg.de -d var/in1000.comment

------------------------
 Nbody6++ Job #1
------------------------

 Configuration:
------------------------------------------------------


  Parameter input file: var/in1000.comment
  Common block file   : n/a
  Initial data file   : n/a
  Host                : dgsi.zah.uni-heidelberg.de
  Job-manager         : GW
  Delegate credential : yes
  Job statistics      : no
  Batch mode          : yes


 Job Preparation:
------------------------------------------------------
Packaging the source code...
The source directory is missing.
Should the sources be downloaded from SVN [y/n]?

Press "y" and "Return"

Which branch should be downloaded [trunk]?

Press "Return"

Getting source code from SVN server...A    nbody6src/configure
A    nbody6src/Makefile.in

...

A    nbody6src/install-sh
Checked out revision 112.
done.

 Job Preparation:
------------------------------------------------------
Packaging the source code...done.
Generating wrapper...done.
Generating job description...done.
EPR will be written to: deleg.epr
Delegated credential EPR:
Address: https://dgsi.zah.uni-heidelberg.de:8443/wsrf/services/DelegationService
Reference property[0]:
<ns1:DelegationKey xmlns:ns1="http://www.globus.org/08/2004/delegationService">bc8918d0-4c33-11e1-be91-a5b0ff78dbf3</ns1:DelegationKey>


 Job Submission:
------------------------------------------------------
globusrun-ws -submit -b -F dgsi.zah.uni-heidelberg.de -Ft GW -S -Jf deleg.epr -o outfiles/1/job.epr -Io outfiles/1/job.uuid -f tmp/nbody6.rsl_1
Delegating user credentials...Done.
Submitting job...Done.
Job ID: uuid:bcb4fdf6-4c33-11e1-8833-000081ce6ef4
Termination time: 02/01/2012 17:48 GMT
Removing .lock
Finalizing done.
agrid107@mintaka:~/nb6deployment$

./status.sh 1
```
Current job state: Pending
```
./status.sh 1
```
Current job state: Active
```
./status.sh 1
```
Current job state: StageOut
```
./status.sh 1
```
Current job state: CleanUp
```
./status.sh 1
```
Current job state: Done
```

Hint: Watch process using gwps -c 1 on dgsi.zah.uni-heidelberg.de, too!

cd outfiles/1/

ls -l

total 76136
-rw-r--r-- 1 agrid107 agrid 38667596 Feb  3 18:07 comm.1
-rw-r--r-- 1 agrid107 agrid 38667596 Feb  3 18:07 comm.2
-rw-r--r-- 1 agrid107 agrid   485188 Feb  3 18:07 conf.3
-rw-r--r-- 1 agrid107 agrid        0 Feb  3 18:07 hia.12
-rw-r--r-- 1 agrid107 agrid      477 Feb  3 18:04 job.epr
-rw-r--r-- 1 agrid107 agrid       41 Feb  3 18:04 job.uuid
-rw-r--r-- 1 agrid107 agrid     2816 Feb  3 18:07 lagr.7
-rw-r--r-- 1 agrid107 agrid    46635 Feb  3 18:07 nbody6.out
-rw-r--r-- 1 agrid107 agrid      222 Feb  3 18:07 wrapper.err
-rw-r--r-- 1 agrid107 agrid    65641 Feb  3 18:07 wrapper.out

cat nbody6.out | grep "ADJUST"

  0 ADJUST:  TIME =    0.00000D+00  T[Myr] =     0.00  Q = 0.50  DE =   0.000000E+00  E =  -2.500000E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    1.00000D+00  T[Myr] =     0.56  Q = 0.49  DE =   1.248276E-07  E =  -2.500000E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    2.00000D+00  T[Myr] =     1.13  Q = 0.49  DE =  -8.818218E-07  E =  -2.500002E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    3.00000D+00  T[Myr] =     1.69  Q = 0.50  DE =   8.124723E-07  E =  -2.500000E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    4.00000D+00  T[Myr] =     2.26  Q = 0.53  DE =   9.164885E-07  E =  -2.499997E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    5.00000D+00  T[Myr] =     2.82  Q = 0.52  DE =   1.103399E-06  E =  -2.499994E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    6.00000D+00  T[Myr] =     3.39  Q = 0.53  DE =  -3.207759E-07  E =  -2.499995E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    7.00000D+00  T[Myr] =     3.95  Q = 0.50  DE =   2.743119E-07  E =  -2.499994E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    8.00000D+00  T[Myr] =     4.52  Q = 0.48  DE =  -2.775261E-07  E =  -2.499995E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    9.00000D+00  T[Myr] =     5.08  Q = 0.55  DE =  -2.473364E-07  E =  -2.499996E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00
  0 ADJUST:  TIME =    1.00000D+01  T[Myr] =     5.65  Q = 0.51  DE =  -1.013946E-07  E =  -2.499996E-01 EBIN=   0.000000E+00 EMERGE=   0.000000E+00

cat nbody6.out | grep "ERRTOT"

  0.7  ERRTOT = 1.40264D-06  DETOT = 3.90889D-07

Back to Installation of GridWay 5.8.1 and GridGateWay 1.0.4

Forward to The GridWay Metascheduler (master document)

Klaus Rieger